© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57505
    Prev
    Next
    INDEX
    Explanations

    zero or false values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /reference
    -0.08
    /master
    -0.08
    erving
    -0.08
    æŁ»
    -0.08
    /store
    -0.08
    è¯ŃçļĦ
    -0.08
    ç»İ
    -0.08
    iny
    -0.07
    _deinit
    -0.07
    æ¯Ķä½ľ
    -0.07
    POSITIVE LOGITS
     except
    0.09
    except
    0.07
     because
    0.07
    olk
    0.06
    éĻ¤éĿŀ
    0.06
    illac
    0.06
    chet
    0.06
     prise
    0.06
    because
    0.06
    ибо
    0.06
    Activations Density 0.004%

    No Known Activations